Heterogeneous Multi-Core Processor Thermal Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile application processors face challenges in balancing high-performance capabilities with low power consumption and heat generation, as high-performance cores consume more power and generate heat, while low-power cores offer slower processing capabilities.
Innovation Solution
A method for operating a heterogeneous multi-core processor that dynamically switches tasks between high-performance/high-power 'big' cores and low-performance/low-power 'little' cores based on temperature thresholds, using in-kernel switching and dynamic voltage and frequency scaling to manage power consumption and thermal management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If the big core is used to provide high-performance processing, then processing speed is improved, but power consumption and heat generation increase
Solution Approach 1:
The system dynamically switches between big core and little core based on workload conditions, temperature thresholds, and performance requirements. The kernel monitors system state and migrates tasks between cores adaptively, allowing the processing architecture to change its configuration in real-time rather than being static
Solution Approach 2:
The system changes operational parameters by switching between different core types with different performance characteristics. When the big core exceeds temperature thresholds, the system changes the active processing unit to the little core, effectively changing the parameter of which core is active to balance performance and power consumption
2Speed
If the big core is used to provide high-performance processing, then processing speed is improved, but heat generation increases
Solution Approach 1:
The system converts the harmful effect of heat generation from the big core into a useful switching condition. When the big core temperature exceeds a threshold, the system automatically migrates tasks to the little core, using the temperature condition as a trigger to switch to a cooler processing unit, thereby preventing thermal issues
Solution Approach 2:
The system dynamically adjusts which core is active based on real-time temperature monitoring. The kernel continuously evaluates temperature thresholds and workload conditions, switching between big and little cores adaptively to maintain thermal management while meeting performance requirements
3Use of energy by moving object
If the little core is used to reduce power consumption, then power efficiency is improved, but processing speed decreases
Solution Approach 1:
The system dynamically selects the appropriate core type based on current workload demands and temperature conditions. The kernel monitors system state and switches between little core (for power efficiency) and big core (for processing speed) adaptively, allowing the system to optimize for either power consumption or processing speed depending on current requirements
Solution Approach 2:
The heterogeneous multi-core processor provides universal processing capability by incorporating both big cores and little cores in the same system. The kernel can distribute tasks across different core types, allowing the system to handle both power-sensitive and performance-sensitive workloads using the appropriate core type for each task
4Temperature
If task switching between cores is implemented, then thermal management is improved, but system complexity increases
Solution Approach 1:
The kernel acts as an intermediary that manages task migration between big and little cores. It monitors temperature thresholds and workload conditions, and automatically performs task switching without requiring complex external control logic, thereby simplifying the overall system architecture while enabling sophisticated thermal management
Solution Approach 2:
The system performs self-service thermal management through automated task migration. The kernel monitors its own thermal state and workload conditions, and automatically switches tasks between cores based on predefined temperature thresholds and performance requirements, eliminating the need for external thermal management hardware or complex control systems
Data Source
AI summary
A method of operating an electronic system including a heterogeneous multi-core processor is provided. The method includes measuring the temperature and/or workload of a big (high-performance) core and switching a current core load from the big core to a small (low-power) core in response to the measured temperature and workload of the big core.